Estimating worst case frontier risks of open weight LLMs

OpenAI studies worst-case frontier risks of releasing gpt-oss by introducing malicious fine-tuning to elicit maximum capabilities in biology and cybersecurity.

From the source
In this paper, we study the worst-case frontier risks of releasing gpt-oss. We introduce malicious fine-tuning (MFT), where we attempt to elicit maximum capabilities by fine-tuning gpt-oss to be as capable as possible in two domains: biology and cybersecurity.
openai.com

Visit source ↗openai.com

Announced: 05 Aug 2025 00:00 UTC
Detected: 03 Aug 2026 21:11 UTC (+363d after)

Other stories

OpenAI · 28 AugOur decision on Cursor following its acquisition by SpaceX

OpenAI · 28 AugSupporting Thailand’s next generation of AI startupsPartnership

Google Research · 27 AugPlanetary prediction engine: Automating global models via Earth AIResearch paper

OpenAI · 27 AugBetter answers, broader thinking: What students gain from ChatGPT and critical-thinking training

Research paper

OpenAI · 27 AugExpanding OpenAI’s presence in BrazilAvailability change

LG AI Research · 27 Aug[ACL 2026] ReSQL: A Self-Improving Text-to-SQL Framework through Retrieval-Augmented Error ReasoningResearch paper